diff --git a/vllm/compilation/backends.py b/vllm/compilation/backends.py
index 5af3b7efed2d6..90795c29ebab7 100644
--- a/vllm/compilation/backends.py
+++ b/vllm/compilation/backends.py
@@ -31,7 +31,7 @@ logger = init_logger(__name__)
 def make_compiler(compilation_config: CompilationConfig) -> CompilerInterface:
     if compilation_config.use_inductor:
         if envs.VLLM_USE_STANDALONE_COMPILE and is_torch_equal_or_newer(
-                "2.8.0"):
+                "2.8.0a"):
             logger.debug("Using InductorStandaloneAdaptor")
             return InductorStandaloneAdaptor()
         else:
diff --git a/vllm/model_executor/layers/quantization/torchao.py b/vllm/model_executor/layers/quantization/torchao.py
index af50b45d44b7f..9c909a3a430cb 100644
--- a/vllm/model_executor/layers/quantization/torchao.py
+++ b/vllm/model_executor/layers/quantization/torchao.py
@@ -44,14 +44,14 @@ class TorchAOConfig(QuantizationConfig):
         """
         # TorchAO quantization relies on tensor subclasses. In order,
         # to enable proper caching this needs standalone compile
-        if is_torch_equal_or_newer("2.8.0"):
+        if is_torch_equal_or_newer("2.8.0a"):
             os.environ["VLLM_TEST_STANDALONE_COMPILE"] = "1"
             logger.info(
                 "Using TorchAO: Setting VLLM_TEST_STANDALONE_COMPILE=1")
 
         # TODO: remove after the torch dependency is updated to 2.8
         if is_torch_equal_or_newer(
-                "2.7.0") and not is_torch_equal_or_newer("2.8.0"):
+                "2.7.0") and not is_torch_equal_or_newer("2.8.0a"):
             os.environ["VLLM_DISABLE_COMPILE_CACHE"] = "1"
             logger.info("Using TorchAO: Setting VLLM_DISABLE_COMPILE_CACHE=1")
         """